update model small

config.json

@@ -1,138 +1,23 @@
 {
-  "_name_or_path": "experiments/model_dbmdz_bert_medium_historic_multilingual_cased_max_sequence_length_512_epochs_5_run_multitask.baseline.False2025/",
   "architectures": [
-    "ExtendedMultitaskTimeModelForTokenClassification"
+    "MultitaskTimeModelForTokenClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
-  "auto_map": {
-    "AutoConfig": "configuration_stacked.ImpressoConfig",
-    "AutoModelForTokenClassification": "modeling_stacked.ExtendedMultitaskTimeModelForTokenClassification"
-  },
   "classifier_dropout": null,
-  "custom_pipelines": {
-    "generic-ner": {
-      "impl": "generic_ner.ExtendedMultitaskTimeModelForTokenClassificationPipeline",
-      "pt": "AutoModelForTokenClassification"
-    }
-  },
+  "dtype": "float32",
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 512,
   "initializer_range": 0.02,
   "intermediate_size": 2048,
-  "label_map": {
-    "NE-COARSE-LIT": {
-      "I-pers": 0,
-      "I-prod": 1,
-      "B-prod": 2,
-      "B-loc": 3,
-      "I-time": 4,
-      "B-pers": 5,
-      "B-org": 6,
-      "B-time": 7,
-      "I-loc": 8,
-      "O": 9,
-      "I-org": 10
-    },
-    "NE-FINE-COMP": {
-      "I-comp.title": 0,
-      "B-comp.title": 1,
-      "I-comp.function": 2,
-      "I-comp.name": 3,
-      "B-comp.function": 4,
-      "O": 5,
-      "B-comp.name": 6
-    }
-  },
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
-  "model_type": "stacked_bert",
+  "model_type": "bert",
   "num_attention_heads": 8,
   "num_hidden_layers": 8,
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
-  "pretrained_config": {
-    "_name_or_path": "dbmdz/bert-medium-historic-multilingual-cased",
-    "add_cross_attention": false,
-    "architectures": [
-      "BertForMaskedLM"
-    ],
-    "attention_probs_dropout_prob": 0.1,
-    "bad_words_ids": null,
-    "begin_suppress_tokens": null,
-    "bos_token_id": null,
-    "chunk_size_feed_forward": 0,
-    "classifier_dropout": null,
-    "cross_attention_hidden_size": null,
-    "decoder_start_token_id": null,
-    "diversity_penalty": 0.0,
-    "do_sample": false,
-    "early_stopping": false,
-    "encoder_no_repeat_ngram_size": 0,
-    "eos_token_id": null,
-    "exponential_decay_length_penalty": null,
-    "finetuning_task": null,
-    "forced_bos_token_id": null,
-    "forced_eos_token_id": null,
-    "hidden_act": "gelu",
-    "hidden_dropout_prob": 0.1,
-    "hidden_size": 512,
-    "id2label": {
-      "0": "LABEL_0",
-      "1": "LABEL_1"
-    },
-    "initializer_range": 0.02,
-    "intermediate_size": 2048,
-    "is_decoder": false,
-    "is_encoder_decoder": false,
-    "label2id": {
-      "LABEL_0": 0,
-      "LABEL_1": 1
-    },
-    "layer_norm_eps": 1e-12,
-    "length_penalty": 1.0,
-    "max_length": 20,
-    "max_position_embeddings": 512,
-    "min_length": 0,
-    "model_type": "bert",
-    "no_repeat_ngram_size": 0,
-    "num_attention_heads": 8,
-    "num_beam_groups": 1,
-    "num_beams": 1,
-    "num_hidden_layers": 8,
-    "num_return_sequences": 1,
-    "output_attentions": false,
-    "output_hidden_states": false,
-    "output_scores": false,
-    "pad_token_id": 0,
-    "position_embedding_type": "absolute",
-    "prefix": null,
-    "problem_type": null,
-    "pruned_heads": {},
-    "remove_invalid_values": false,
-    "repetition_penalty": 1.0,
-    "return_dict": true,
-    "return_dict_in_generate": false,
-    "sep_token_id": null,
-    "suppress_tokens": null,
-    "task_specific_params": null,
-    "temperature": 1.0,
-    "tf_legacy_loss": false,
-    "tie_encoder_decoder": false,
-    "tie_word_embeddings": true,
-    "tokenizer_class": null,
-    "top_k": 50,
-    "top_p": 1.0,
-    "torch_dtype": null,
-    "torchscript": false,
-    "type_vocab_size": 2,
-    "typical_p": 1.0,
-    "use_bfloat16": false,
-    "use_cache": true,
-    "vocab_size": 32000
-  },
-  "torch_dtype": "float32",
-  "transformers_version": "4.40.0.dev0",
+  "transformers_version": "4.57.0.dev0",
   "type_vocab_size": 2,
   "use_cache": true,
   "vocab_size": 32000

label_map.json

@@ -1 +1 @@
-{"NE-COARSE-LIT": {"I-pers": 0, "I-prod": 1, "B-prod": 2, "B-loc": 3, "I-time": 4, "B-pers": 5, "B-org": 6, "B-time": 7, "I-loc": 8, "O": 9, "I-org": 10}, "NE-FINE-COMP": {"I-comp.title": 0, "B-comp.title": 1, "I-comp.function": 2, "I-comp.name": 3, "B-comp.function": 4, "O": 5, "B-comp.name": 6}}
+{"NE-COARSE-LIT": {"B-loc": 0, "B-org": 1, "I-pers": 2, "B-pers": 3, "I-loc": 4, "I-org": 5, "O": 6}, "NE-FINE-COMP": {"B-comp.title": 0, "I-comp.name": 1, "I-comp.title": 2, "I-comp.function": 3, "B-comp.name": 4, "B-comp.function": 5, "O": 6}}

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4693904ab70f0ef7c0249db6c23b0b1e3b2760629d8dafa9010f5ec9feb7de39
-size 168604214
+oid sha256:d85dc101a70451930bedc505f6ba1b231f42dc8b84795c5515f43e5d715be0a2
+size 168596022

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc92dca5d693d80c40bfa708d0ee9551d1f85b832c57710b3edfc72dc86707e1
+oid sha256:a0eae1fb01475a2434e6ce45356e764e9d567efedff16ac7ee77c63b9a6e4e2c
 size 2104